The role of artificial intelligence in surgical patient perioperative management

Revolutionizing Patient Care: A Comprehensive Review of Artificial Intelligence Applications in Anesthesia

This review explores the intersection of artificial intelligence (AI) and anesthesia, examining its transformative impact on patient care across various phases. Beginning with a historical overview of anesthesia, we highlight the critical role of technological advancements in ensuring optimal patient outcomes. The emergence of AI in healthcare sets the stage for a comprehensive analysis of its applications in anesthesia. In the preoperative phase, AI facilitates personalized risk assessments and decision support, optimizing anesthesia planning and drug dosage predictions. Moving to the intraoperative phase, we delve into AI's role in monitoring and control through sophisticated anesthesia monitoring and closed-loop systems. Additionally, we discuss the integration of robotics and AI-guided procedures, revolutionizing surgical assistance. Transitioning to the postoperative phase, we explore AI-driven postoperative monitoring, predictive analysis for complications, and the integration of AI into rehabilitation programs and long-term follow-up. These new applications redefine patient recovery, emphasizing personalized care and proactive interventions. However, the integration of AI in anesthesia poses challenges and ethical considerations. Data security, interpretability, and bias in AI algorithms demand scrutiny. Moreover, the evolving patient-doctor relationship in an AI-driven care landscape requires a delicate balance between efficiency and human touch. Looking forward, we discuss the future directions of AI in anesthesia, anticipating advances in technology and AI algorithms. The integration of AI into routine clinical practice and its potential impact on anesthesia education and training are explored, emphasizing the need for collaboration, education, and ethical guidelines. This review provides a comprehensive overview of AI applications in anesthesia, offering insights into the present landscape, challenges, and future directions. The synthesis of historical perspectives, current applications, and future possibilities underscores the transformative potential of AI in revolutionizing patient care within the dynamic field of anesthesia.

Deep learning for anatomical interpretation of video bronchoscopy images

Anesthesiologists commonly use video bronchoscopy to facilitate intubation or confirm the location of the endotracheal tube; however, depth and orientation in the bronchial tree can often be confused because anesthesiologists cannot trace the airway from the oropharynx when it is performed using an endotracheal tube. Moreover, the decubitus position is often used in certain surgeries. Although it occurs rarely, the misinterpretation of tube location can cause accidental extubation or endobronchial intubation, which can lead to hyperinflation. Thus, video bronchoscopy with a decision supporting system using artificial intelligence would be useful in the anesthesiologic process. In this study, we aimed to develop an artificial intelligence model robust to rotation and covering using video bronchoscopy images. We collected video bronchoscopic images from an institutional database. Collected images were automatically labeled by an optical character recognition engine as the carina and left/right main bronchus. Except 180 images for the evaluation dataset, 80% were randomly allocated to the training dataset. The remaining images were assigned to the validation and test datasets in a 7:3 ratio. Random image rotation and circular cropping were applied. Ten kinds of pretrained models with < 25 million parameters were trained on the training and validation datasets. The model showing the best prediction accuracy for the test dataset was selected as the final model. Six human experts reviewed the evaluation dataset for the inference of anatomical locations to compare its performance with that of the final model. In the experiments, 8688 images were prepared and assigned to the evaluation (180), training (6806), validation (1191), and test (511) datasets. The EfficientNetB1 model showed the highest accuracy (0.86) and was selected as the final model. For the evaluation dataset, the final model showed better performance (accuracy, 0.84) than almost all human experts (0.38, 0.44, 0.51, 0.68, and 0.63), and only the most-experienced pulmonologist showed performance comparable (0.82) with that of the final model. The performance of human experts was generally proportional to their experiences. The performance difference between anesthesiologists and pulmonologists was marked in discrimination of the right main bronchus. Using bronchoscopic images, our model could distinguish anatomical locations among the carina and both main bronchi under random rotation and covering. The performance was comparable with that of the most-experienced human expert. This model can be a basis for designing a clinical decision support system with video bronchoscopy.